/awesome-3d-human-reconstruction

nerf or pifu

  • StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision paper
  • Learning Implicit 3D Representations of Dressed Humans from Sparse Views paper
  • Animatable Neural Radiance Fields for Human Body Modeling paper
  • PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction paper code
  • Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control paper&code
  • MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras paper
  • DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering paper
  • Bridge the Gap Between Model-based and Model-free Human Reconstruction paper
  • MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images paper
  • Animatable Neural Radiance Fields from Monocular RGB Video paper
  • Few-shot Neural Human Performance Rendering from Sparse RGBD Videos paper
  • Relightable Neural Video Portrait paper
  • FLAME-in-NeRF : Neural control of Radiance Fields for Free View Face Animation paper
  • ARCH++: Animation-Ready Clothed Human Reconstruction Revisited paper
  • Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing paper
  • Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering paper code
  • Topologically Consistent Multi-View Face Inference Using Volumetric Sampling paper
  • Creating and Reenacting Controllable 3D Humans with Differentiable Rendering paper
  • H-NeRF: Neural Radiance Fields for Rendering and Temporal Reconstruction of Humans in Motion paper
  • FENeRF: Face Editing in Neural Radiance Fields paper
  • LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies paper&code
  • Neural Head Avatars from Monocular RGB Videos paper
  • HumanNeRF: Generalizable Neural Human Radiance Field from Sparse Inputs paper
  • Implicit Neural Deformation for Multi-View Face Reconstruction paper
  • MoFaNeRF: Morphable Facial Neural Radiance Field paper code
  • Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering paper
  • HeadNeRF: A Real-time NeRF-based Parametric Head Model paper
  • I M Avatar: Implicit Morphable Head Avatars from Videos paper
  • LookinGoodĎ€: Real-time Person-independent Neural Re-rendering for High-quality Human Performance Capture paper
  • ICON: Implicit Clothed humans Obtained from Normals paper code
  • DD-NeRF: Double-Diffusion Neural Radiance Field as a Generalizable Implicit Body Representation paper
  • Human View Synthesis using a Single Sparse RGB-D Input paper
  • Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis paper
  • Embodied Hands: Modeling and Capturing Hands and Bodies Together paper
  • HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video paper
  • gDNA: Towards Generative Detailed Neural Avatars paper code

3D human whole body

  • Collaborative Regression of Expressive Bodies using Moderation paper&code
  • Monocular Real-time Full Body Capture with Inter-part Correlations paper&code
  • Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data paper&code
  • Real-time RGBD-based Extended Body Pose Estimation paper code
  • Detailed Avatar Recovery from Single Image paper
  • Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras paper

3D human reconstruction

  • Monocular Expressive Body Regression through Body-Driven Attention paper code
  • FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration paper code
  • Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose paper code
  • Monocular Real-Time Volumetric Performance Capture paper code
  • Full-Body Awareness from Partial Observations paper code
  • CenterHMR: a Bottom-up Single-shot Method for Multi-person 3D Mesh Recovery from a Single Image paper code
  • Reconstructing NBA players paper code
  • Going beyond Free Viewpoint: Creating Animatable Volumetric Video of Human Performances paper
  • Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild paper code
  • MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video paper
  • Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People paper code
  • Synthetic Training for Monocular Human Mesh Recovery paper
  • Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation paper
  • Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture
  • 4D Human Body Capture from Egocentric Video via 3D Scene Grounding paper
  • HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation paper code
  • We are More than Our Joints: Predicting how 3D Bodies Move paper
  • SMPLy Benchmarking 3D Human Pose Estimation in the Wild paper
  • Synthesizing Long-Term 3D Human Motion and Interaction in 3D paper
  • Detailed 3D Human Body Reconstruction from Multi-view Images Combining Voxel Super-Resolution and Learned Implicit Representation
  • A novel joint points and silhouette-based method to estimate 3D human pose and shape
  • FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction paper
  • NerFACE: Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction code
  • Learning Complex 3D Human Self-Contact paper
  • Populating 3D Scenes by Learning Human-Scene Interaction paper
  • ANR: Articulated Neural Rendering for Virtual Avatars paper
  • Human Mesh Recovery from Multiple Shots paper
  • Lifting 2D StyleGAN for 3D-Aware Face Generation [paper](S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling)
  • Capturing Detailed Deformations of Moving Human Bodies paper
  • 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos paper
  • ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References paper
  • SMPLicit: Topology-aware Generative Model for Clothed People paper&code
  • Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos paper
  • NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras paper
  • Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild paper
  • 3DCrowdNet: 2D Human Pose-Guided 3D Crowd Human Pose and Shape Estimation in the Wild paper
  • SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements paper
  • Multi-person Implicit Reconstruction from a Single Image paper
  • PARE: Part Attention Regressor for 3D Human Body Estimation paper code
  • Temporal Consistency Loss for High Resolution Textured and Clothed 3D Human Reconstruction from Monocular Video paper
  • Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors paper
  • End-to-End Human Pose and Mesh Reconstruction with Transformers paper
  • Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation paper
  • SHARP: Shape-Aware Reconstruction of People In Loose Clothing paper
  • THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers paper
  • Deep3DPose: Realtime Reconstruction of Arbitrarily Posed Human Bodies from Single RGB Images paper
  • Learning Local Recurrent Models for Human Mesh Recovery paper
  • PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time paper
  • LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering paper
  • Learning Motion Priors for 4D Human Body Capture in 3D Scenes paper code
  • Probabilistic Modeling for Human Mesh Recovery paper&code
  • DC-GNet: Deep Mesh Relation Capturing Graph Convolution Network for 3D Human Shape Reconstruction paper
  • Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation paper code
  • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE code
  • Learning to Regress Bodies from Images using Differentiable Semantic Rendering paper
  • Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation paper
  • UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model paper
  • Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images paper code
  • Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise paper
  • 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning paper code
  • Out-of-Domain Human Mesh Reconstruction via Bilevel Online Adaptation paper code
  • Monocular Human Shape and Pose with Dense Mesh-borne Local Image Features paper
  • Human Performance Capture from Monocular Video in the Wild paper
  • Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model paper
  • GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras paper
  • MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images} paper code
  • EgoBody: Human Body Shape, Motion and Social Interactions from Head-Mounted Devices paper code
  • Putting People in their Place: Monocular Regression of 3D People in Depth paper
  • Multi-initialization Optimization Network for Accurate 3D Human Pose and Shape Estimation paper
  • moothNet: A Plug-and-Play Network for Refining Human Poses in Videos paper
  • HSPACE: Synthetic Parametric Humans Animated in Complex Environments paper

3D human hand

  • Active Learning for Bayesian 3D Hand Pose Estimation paper code
  • Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People paper code
  • EventHands: Real-Time Neural 3D Hand Reconstruction from an Event Stream
  • Monocular Real-time Full Body Capture with Inter-part Correlations
  • Im2Mesh GAN: Accurate 3D Hand Mesh Recovery from a Single RGB Image
  • HandTailor: Towards High-Precision Monocular 3D Hand Recovery paper code
  • Camera-Space Hand Mesh Recovery via Semantic Aggregation and Adaptive 2D-1D Registration paper code
  • Model-based 3D Hand Reconstruction via Self-Supervised Learning paper code
  • Action-Conditioned 3D Human Motion Synthesis with Transformer VAE paper
  • Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time paper
  • RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video paper
  • ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis paper code
  • Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements paper code
  • Dynamic Iterative Refinement for Efficient 3D Hand Pose Estimation paper
  • Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation paper
  • MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image paper code

3d human face

  • High-Fidelity 3D Digital Human Creation from RGB-D Selfies paper code
  • StyleUV: Diverse and High-quality UV Map Generative Model paper
  • i3DMM: Deep Implicit 3D Morphable Model of Human Heads paper
  • Relightable 3D Head Portraits from a Smartphone Video paper
  • Learning Compositional Radiance Fields of Dynamic Human Heads paper
  • SIDER : Single-Image Neural Optimization for Facial Geometric Detail Recovery paper
  • Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry paper code
  • HIGH-QUALITY REAL TIME FACIAL CAPTURE BASED ON SINGLE CAMERA paper
  • Self-supervised High-fidelity and Re-renderable 3D Facial Reconstruction from a Single Imag paper
  • Generating Diverse 3D Reconstructions from a Single Occluded Face Image paper
  • Self-Supervised Robustifying Guidance for Monocular 3D Face Reconstruction paper

3d human head

  • Pixel Codec Avatars paper
  • H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction paper

texture

  • Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera paper
  • Semi-supervised Synthesis of High-Resolution Editable Textures for 3D Humans paper

skin

  • HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction paper

pose estimation

  • CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild paper
  • Active Learning for Bayesian 3D Hand Pose Estimation paper code
  • A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering
  • HandsFormer: Keypoint Transformer for Monocular 3D Pose Estimation of Hands and Object in Interaction paper
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation paper
  • Multi-Person Extreme Motion Prediction with Cross-Interaction Attention paper
  • VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild paper
  • Gravity-Aware Monocular 3D Human-Object Reconstruction paper&code
  • DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to the Third Dimension paper
  • Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images paper
  • Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos paper
  • Physics-based Human Motion Estimation and Synthesis from Videos paper
  • Real-time, low-cost multi-person 3D pose estimation paper
  • Direct Multi-view Multi-person 3D Human Pose Estimation paper code
  • Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation code
  • Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning paper
  • In-Bed Human Pose Estimation from Unseen and Privacy-Preserving Image Domains paper
  • Camera Motion Agnostic 3D Human Pose Estimation paper code
  • ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses paper
  • Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving paper
  • AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation paper

registration

  • LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration paper code
  • Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction paper
  • FARM: Functional Automatic Registration Method for 3D Human Bodies paper code
  • Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration paper
  • Unsupervised 3D Human Mesh Recovery from Noisy Point Clouds paper

others

  • Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On paper
  • TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style paper code
  • 3DBooSTeR: 3D Body Shape and Texture Recovery paper
  • Neural 3D Clothes Retargeting from a Single Image paper
  • Single-image Full-body Human Relighting paper
  • iButter: Neural Interactive Bullet Time Generator for Human Free-viewpoint Rendering paper
  • A Riemannian Framework for Analysis of Human Body Surface paper
  • The Power of Points for Modeling Humans in Clothing paper&code
  • Neural Human Deformation Transfer paper
  • 3D Human Texture Estimation from a Single Image with Transformers paper
  • Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks paper
  • ZFlow: Gated Appearance Flow-based Virtual Try-on with 3D Priors paper
  • A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis paper code
  • Action2video: Generating Videos of Human 3D Actions paper
  • Garment4D: Garment Reconstruction from Point Cloud Sequences paper code

correspondence

  • HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences paper

application

  • One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing paper
  • LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization paper
  • ARShoe: Real-Time Augmented Reality Shoe Try-on System on Smartphones paper
  • A Neural Anthropometer Learning from Body Dimensions Computed on Human 3D Meshes paper
  • Robust 3D Garment Digitization from Monocular 2D Images for 3D Virtual Try-On Systems paper

human mattting

  • Real-Time High-Resolution Background Matting code
  • Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems paper
  • DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes paper
  • PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset paper code

parametric model

body

  • SMPL: A Skinned Multi-Person Linear Model paper code
  • Expressive Body Capture: 3D Hands, Face, and Body from a Single Image paper code
  • STAR: Sparse Trained Articulated Human Body Regressor paper code

face

head

  • FLAME: Articulated Expressive Head Model website

dataset

  • MAAD-Face: A Massively Annotated Attribute Dataset for Face Images paper
  • NTU60-X: TOWARDS SKELETON-BASED RECOGNITION OF SUBTLE HUMAN ACTIONS code
  • K-Hairstyle: A Large-scale Korean hairstyle dataset for virtual hair editing and hairstyle classification homepage
  • AGORA: Avatars in Geography Optimized for Regression Analysis homepage
  • FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction paper
  • Simulated garment dataset for virtual try-on address
  • Reconstructing Hand-Object Interactions in the Wild github
  • ASL-Skeleton3D and ASL-Phono: Two Novel Datasets for the American Sign Language paper
  • AMASS: Archive of Motion Capture as Surface Shapes paper github

labs

other related awesome

  • awesome-clothed-human github
  • curated-list-of-awesome-3D-Morphable-Model-software-and-data github
  • awesome-hand-pose-estimation github
  • Awesome 3D Body Papers github